Andrea Zignoli

In the last few years, the rapid spread of new wearable technologies in the sport and health industries is enabling the collection of an overwhelming amount of data. As we further progress in our data collection we soon realise that we need to make the best out of our sensors and make an efficient usage of the available data. In this module, we will explore different methodologies that aim at improving your ability in 1) correctly interpret the data, 2) discern what is useful from what is useless and 3) make data-driven and objective choices. By using real-world training data files, we will develop interpretative modes (that you can easily deploy on spreadsheets, Matlab or Python scripts) with a hands-on approach. Hopefully, you will soon realise that, with the right tools in your hands, even a single training data file can hide a gold mine of information.

Andrea Zignoli currently holds a post-doc scholarship at the University of Trento (I). His CV is multidisciplinary and includes a number of international collaborations. He conducted his Master degree in Mechatronics Engineering (2009-2011) across the University of Trento (I) and Nottingham (UK), he conducted his PhD in Movement Science (2013-2015) across the Universities of Verona (I) and Calgary (AB) and then he advanced to his first post-doctoral position at the University of Yokohama (J). Computational modelling and the application of optimal control techniques to predictive problems are the starting point of his research directions, which include musculoskeletal dynamics, rehabilitation robots, human bioenergetics and locomotion. He is currently developing and applying AI techniques to the processing of running kinematics, training (athletica.ai) and cardiopulmonary test data (oxynet.net).